Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Hu, Xuran, Zhu, Mingzhe, Liu, Yuanjing, Feng, Zhenpeng, Stankovic, LJubisa
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2401.03128
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916081865588736
author Hu, Xuran
Zhu, Mingzhe
Liu, Yuanjing
Feng, Zhenpeng
Stankovic, LJubisa
author_facet Hu, Xuran
Zhu, Mingzhe
Liu, Yuanjing
Feng, Zhenpeng
Stankovic, LJubisa
contents Explainable artificial intelligence (XAI) holds immense significance in enhancing the deep neural network's transparency and credibility, particularly in some risky and high-cost scenarios, like synthetic aperture radar (SAR). Shapley is a game-based explanation technique with robust mathematical foundations. However, Shapley assumes that model's features are independent, rendering Shapley explanation invalid for high dimensional models. This study introduces a manifold-based Shapley method by projecting high-dimensional features into low-dimensional manifold features and subsequently obtaining Fusion-Shap, which aims at (1) addressing the issue of erroneous explanations encountered by traditional Shap; (2) resolving the challenge of interpretability that traditional Shap faces in complex scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03128
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Manifold-based Shapley for SAR Recognization Network Explanation
Hu, Xuran
Zhu, Mingzhe
Liu, Yuanjing
Feng, Zhenpeng
Stankovic, LJubisa
Artificial Intelligence
H.1.m
Explainable artificial intelligence (XAI) holds immense significance in enhancing the deep neural network's transparency and credibility, particularly in some risky and high-cost scenarios, like synthetic aperture radar (SAR). Shapley is a game-based explanation technique with robust mathematical foundations. However, Shapley assumes that model's features are independent, rendering Shapley explanation invalid for high dimensional models. This study introduces a manifold-based Shapley method by projecting high-dimensional features into low-dimensional manifold features and subsequently obtaining Fusion-Shap, which aims at (1) addressing the issue of erroneous explanations encountered by traditional Shap; (2) resolving the challenge of interpretability that traditional Shap faces in complex scenarios.
title Manifold-based Shapley for SAR Recognization Network Explanation
topic Artificial Intelligence
H.1.m
url https://arxiv.org/abs/2401.03128